Forecasting the length-of-stay of pediatric patients in hospitals: a scoping review

Abstract

Background Healthcare management faces complex challenges in allocating hospital resources, and predicting patients’ length-of-stay (LOS) is critical in effectively managing those resources. This work aims to map approaches used to forecast the LOS of Pediatric Patients in Hospitals (LOS–P) and patients’ populations and environments used to develop the models. Methods Using the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) methodology, we performed a scoping review that identified 28 studies and analyzed them. The search was conducted on four databases (Science Direct, Scopus, Web of Science, and Medline). The identification of relevant studies was structured around three axes related to the research questions: (i) forecast models, (ii) hospital length-of-stay, and (iii) pediatric patients. Two authors carried out all stages to ensure the reliability of the review process. Articles that passed the initial screening had their data charted on a spreadsheet. Methods reported in the literature were classified according to the stage in which they are used in the modeling process: (i) pre-processing of data, (ii) variable selection, and (iii) cross-validation. Results Forecasting models are most often applied to newborn patients and, consequently, in neonatal intensive care units. Regression analysis is the most widely used modeling approach; techniques associated with Machine Learning are still incipient and primarily used in emergency departments to model patients in specific situations. Conclusions The studies’ main benefits include informing family members about the patient’s expected discharge date and enabling hospital resources’ allocation and planning. Main research gaps are associated with the lack of generalization of forecasting models and limited reported applicability in hospital management. This study also provides a practical guide to LOS–P forecasting methods and a future research agenda.

Análise das variáveis relacionadas ao tempo de permanência da UTI pediátrica de um Câncer center em São Paulo

“…Entretanto, as causas de internação variam amplamente na literatura, uma revisão sistemática 7 realizada com artigos internacionais no período de 1987 a 2017 com tempo de permanência médio de 3,39 dias a 18,02 meses identificou que a maioria dos estudos realizados na temática pediátrica em relação ao tempo de internação são nas UTIP neonatais e hospitais psiquiátricos e que um dos fatores prevalentes nesses estudos são crianças internadas com neoplasia hematológica por neutropenia febril. Todavia, dados da AMIB 9 mostraram que 43,75% das internações clínicas eram por causas infecciosas e a maior causa de internação cirúrgica era por problemas no sistema nervoso central (17,89%).…”

Opportunities and Challenges of Prognostic Models for Extremely Preterm Infants

“…Furthermore, prognostic models may be useful tools to help hospitals and healthcare systems to allocate resources efficiently [25][26][27][28]. By predicting the likelihood of, e.g., the length of hospital stay and adverse outcomes, healthcare facilities can plan ahead for the necessary beds and equipment, and for follow-up care that may be required to meet the specific needs of EPIs [25][26][27][28].…”

Machine learning models to predict and benchmark PICU length of stay with application to children with critical bronchiolitis

“…As a quality measure, hospital LOS is reported to Centers for Medicare and Medicaid Services as part of the Hospital Inpatient Quality Reporting Program, and to the Agency for Healthcare Research and Quality 1,2 . Prior studies have attempted to use large clinical and administrative databases to accurately predict hospital LOS using both traditional statistical methods, 3,4 and machine learning methods 5–12 . While previous machine learning models have been applied to various specialties and clinical settings, few have been built specifically to predict LOS in the pediatric intensive care unit (PICU).…”

“…1,2 Prior studies have attempted to use large clinical and administrative databases to accurately predict hospital LOS using both traditional statistical methods, 3,4 and machine learning methods. [5][6][7][8][9][10][11][12] While previous machine learning models have been applied to various specialties and clinical settings, few have been built specifically to predict LOS in the pediatric intensive care unit (PICU).…”

“…17 For these reasons, we chose to use critical bronchiolitis as the population of interest to develop both a predictive model and benchmarking model for PICU length of stay. Pediatric hospital LOS prediction by machine learning methodology has been advocated for in the published literature 6 as it allows for the selection of variables influential in the prediction of patient LOS without a priori identification by clinicians.…”